papers

Publications (9)

cs.CL2020

Grounded Language Learning Fast and Slow

Felix Hill, Olivier Tieleman, Tamara von Glehn +3

Recent work has shown that large text-based neural language models, trained with conventional supervised learning objectives, acquire a surprising propensity for few- and one-shot…

cs.AI2024

Bad Students Make Great Teachers: Active Learning Accelerates Large-Scale Visual Understanding

Talfan Evans, Shreya Pathak, Hamza Merzic +3

Power-law scaling indicates that large-scale training with uniform sampling is prohibitively slow. Active learning methods aim to increase data efficiency by prioritizing learning…

cs.LG2020

Causally Correct Partial Models for Reinforcement Learning

Danilo J. Rezende, Ivo Danihelka, George Papamakarios +11

In reinforcement learning, we can learn a model of future observations and rewards, and use it to plan the agent's next actions. However, jointly modeling future observations can b…

cs.RO2024

Scaling Instructable Agents Across Many Simulated Worlds

SIMA Team, Maria Abi Raad, Arun Ahuja +91

Building embodied AI systems that can follow arbitrary language instructions in any 3D environment is a key challenge for creating general AI. Accomplishing this goal requires lear…

cs.LG2022

Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning

DeepMind Interactive Agents Team, Josh Abramson, Arun Ahuja +22

A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through…

cs.LG2019

Shaping Belief States with Generative Environment Models for RL

Karol Gregor, Danilo Jimenez Rezende, Frederic Besse +3

When agents interact with a complex environment, they must form and maintain beliefs about the relevant aspects of that environment. We propose a way to efficiently train expressiv…

cs.AI2020

Probing Emergent Semantics in Predictive Agents via Question Answering

Abhishek Das, Federico Carnevale, Hamza Merzic +8

Recent work has shown how predictive modeling can endow agents with rich knowledge of their surroundings, improving their ability to act in complex environments. We propose questio…

cs.LG2024

Data curation via joint example selection further accelerates multimodal learning

Talfan Evans, Nikhil Parthasarathy, Hamza Merzic +1

Data curation is an essential component of large-scale pretraining. In this work, we demonstrate that jointly selecting batches of data is more effective for learning than selectin…

cs.RO2018

Leveraging Contact Forces for Learning to Grasp

Hamza Merzic, Miroslav Bogdanovic, Daniel Kappler +2

Grasping objects under uncertainty remains an open problem in robotics research. This uncertainty is often due to noisy or partial observations of the object pose or shape. To enab…